GANSim-surrogate: An integrated framework for stochastic conditional geomodelling

Song, Suihong1,2; Zhang, Dongxiao3,4; Mukerji, Tapan2; Wang, Nanzhe5,6

2023-05-01

10.1016/j.jhydrol.2023.129493

JOURNAL OF HYDROLOGY   影响因子和分区

0022-1694

1879-2707

Stochastic conditional geomodelling requires effective integration of geological patterns and various types of data, which is crucial but challenging. To address this, we propose a deep-learning framework (GANSim-sur-rogate) for conditioning geomodels to static well facies data, facies probability maps, and non-spatial global features, as well as dynamic time-dependent pressure or flow rate data observed at wells. The framework consists of a Convolutional Neural Network (CNN) generator trained from GANSim (a Generative Adversarial Network -based geomodelling simulation approach), a CNN-based surrogate, and options for searching appropriate input latent vectors for the generator. The four search methods investigated are Markov Chain Monte Carlo, Iterative Ensemble Smoother, gradient descent, and gradual deformation. The framework is validated with channelized reservoirs. First, a generator is trained using GANSim to generate geological facies models; in addition, a flow simulation surrogate is trained using a physics-informed approach. Then, given well facies data, facies proba-bility maps, global facies proportions, and dynamic bottomhole pressure data (BHP), the trained generator takes the first three static conditioning data and a latent vector as inputs and produces a random realistic facies model conditioned to the three static data. To condition to the dynamic data, the produced facies model is converted to permeability property and mapped to BHP data by the trained surrogate. Finally, the mismatch between the surrogate-produced and the observed BHP data is minimized to obtain appropriate input latent vectors which are further mapped into appropriate facies models through the generator. These facies models prove to be realistic and consistent with all of the conditioning data, and the framework is computationally efficient.

GANSim Stochastic geomodelling Uncertainty quantification Surrogate Generative Adversarial Networks (GANs) Convolutional Neural Networks (CNNs) Physics-informed neural networks (PINNs)

SCI ; EI

英语

通讯

National Natural Science Foundation of China[52288101]

Engineering ; Geology ; Water Resources

Engineering, Civil ; Geosciences, Multidisciplinary ; Water Resources

WOS:000990444800001

ELSEVIER

20231714025613

Convolution ; Convolutional neural networks ; Deep learning ; Dynamics ; Geology ; Gradient methods ; Markov processes ; Monte Carlo methods ; Stochastic models ; Stochastic systems

Ergonomics and Human Factors Engineering:461.4 ; Geology:481.1 ; Information Theory and Signal Processing:716.1 ; Artificial Intelligence:723.4 ; Control Systems:731.1 ; Numerical Methods:921.6 ; Probability Theory:922.1 ; Mathematical Statistics:922.2 ; Systems Science:961

ENGINEERING

Web of Science

1.Peng Cheng Lab, Dept Math & Theories, Shenzhen 518000, Peoples R China
2.Stanford Univ, Dept Energy Sci & Engn, 367 Panama St, Stanford, CA 94305 USA
3.Eastern Inst Technol, Eastern Inst Adv Study, Ningbo 315200, Zhejiang, Peoples R China
4.Southern Univ Sci & Technol, Natl Ctr Appl Math Shenzhen NCAMS, Shenzhen 518000, Peoples R China
5.Peking Univ, Coll Engn, BIC, ERE,ESAT, Beijing 100871, Peoples R China
6.Peking Univ, Coll Engn, SKLTCS, Beijing 100871, Peoples R China

Song, Suihong,Zhang, Dongxiao,Mukerji, Tapan,et al. GANSim-surrogate: An integrated framework for stochastic conditional geomodelling[J]. JOURNAL OF HYDROLOGY,2023,620.

Song, Suihong,Zhang, Dongxiao,Mukerji, Tapan,&Wang, Nanzhe.(2023).GANSim-surrogate: An integrated framework for stochastic conditional geomodelling.JOURNAL OF HYDROLOGY,620.

Song, Suihong,et al."GANSim-surrogate: An integrated framework for stochastic conditional geomodelling".JOURNAL OF HYDROLOGY 620(2023).